Organizations: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798 · Integrated Systems Laboratory, ETH Zürich, 8092 Zürich, Switzerland · Department of Engineering “Enzo Ferrari” (DIEF), University of Modena and Reggio Emilia, 41125 Modena, Italy · Department of Electrical, Electronic and Information Engineering “Guglielmo Marconi” (DEI), University of Bologna, 40136 Bologna, Italy · College of Computing and Data Science, Nanyang Technological University, Singapore 639798
We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling rates, while unseen setups reuse the backbone via lightweight adapters. We pre-train a 30M-parameter EEG model on over 15M windows (19--128 channels), alongside ECG (30M) and sEMG (12M) encoders. Across four EEG routes, scale folding cuts Transformer latency by 4.0--7.2x and peak memory by 6.8--12.7x over scale expansion without accuracy loss. Our EEG encoder leads 8 of 9 metrics against BENDR, BIOT, LaBraM, and EEGPT, and surpasses LUNA-L on wearable seizure detection with fewer parameters. Reliability-aware latent fusion (RALF) further integrates summary tokens from independently pre-trained encoders via sample-adaptive weights. On SeizeIT2, RALF raises event sensitivity at 11 false alarms/h from 61.4% to 74.4% and window AUPRC from 0.321 to 0.399 over the best unimodal baseline, outperforming weighted-logit and concatenation fusion across all variants. PhysioWave-T also achieves state-of-the-art sEMG accuracies and top macro-F1 on PTB-XL Super and Chapman-Shaoxing. Code and models: https://github.com/ForeverBlue816/PhysioWave.
Figures & tables
Fig. 1: Overview of PhysioWave-T, shown for EEG. (a) Channel count and sampling rate select a route-specific front end. (b) Adaptive wavelet decomposition and dynamic scale folding produce one C×T signal. (c) Spectral importance of clean-view tokens selects masked patches, zeroed before the online front end. (d) A shared Transformer and two MLP heads reconstruct raw and folded-wavelet patches against stop-gradient targets.
Fig. 2: Soft-gated wavelet analysis. Channel-specific gates blend the upsampled subbands with the running approximation and detail states.
Fig. 3: Cross-scale channel-aggregation feed-forward network (CAFFN). The current approximation–detail pair is refined through convolution, channel aggregation, and attention to shallower-level features.
Fig. 4: Masked reconstruction on four EEG routes spanning 19–128 channels, with 70 % of patches masked. (a) Raw-EEG head. (b) Folded-wavelet head. Columns show the target, masked input, reconstruction, and absolute error on masked patches; r is the masked-patch correlation. Each row shows the median-NMSE validation window of its route, with target-derived color limits.
Fig. 5: Single-channel views of the windows in Fig. 4 : F4, P8, F4, and E40, respectively. Targets are gray; predictions and absolute errors are shown on masked patches. Correlation and normalized mean squared error (NMSE) are evaluated on masked samples.
Fig. 6: Reliability-aware latent fusion (RALF) of 4-s EEG, ECG, and EMG windows. Reliability scores gate tokens and weight unimodal predictions. Orange symbols denote training losses; the trace shows seizure probability over a 60-s test excerpt with a 0.5 threshold.
Modality
Corpus
Route (C,f)
Windows
TUEG [ 31 ]
(19, 256)
13,710,516
HBN [ 32 ]
(128, 512)
1,352,818
FACED [ 33 ]
(32, 512)
129,268
TDBRAIN [ 34 ]
(32, 512)
86,991
M3CV [ 35 ]
(64, 256)
81,895
PhysioNet MI [ 36 ]
(64, 256)
36,933
TABLE I: Pre-training corpora and input configurations. The route (C,f) gives channel count and sampling rate in Hz. Counts refer to processed training windows.
Sleep-EDFx
PhysioNet-P300
KaggleERN
Method
Params
BAC
Kappa
W-F1
BAC
Kappa
AUROC
BAC
Kappa
AUROC
BENDR Front. Hum. Neurosci.’21
157M
0.6655
0.6659
0.7507
0.6114
0.2227
0.6588
0.5672
0.1461
0.6030
BIOT NeurIPS’23
3.2M
0.6622
0.6461
0.7415
0.5485
0.0968
0.5308
0.5118
0.0297
0.5495
LaBraM ICLR’24
5.8M
0.6771
0.6710
0.7592
0.6477
0.2935
0.7068
0.5439
0.0944
0.5693
EEGPT NeurIPS’24
25M
0.6917
0.6857
0.7654
0.6502
0.2999
0.7168
0.5837
0.1882
0.6621
PhysioWave-T (scratch)
30M
0.6924
0.7363
0.8043
0.6512
0.2337
0.7194
0.5704
0.1409
0.6001
TABLE II: EEG classification: balanced accuracy (BAC), Cohen’s kappa, weighted F1 (W-F1), and AUROC. Our values are three-seed means; evaluation splits are specified in the text. Bold purple : highest reported value; underline : second highest.
PTB-XL Super
CPSC 2018
Chapman
Method
Params
F1
AUC
F1
AUC
F1
AUC
MERL ICML’24
11M
48.1
91.9
72.8
92.6
—
87.9
MaeFE TIM’23
9M
64.7
88.6
71.6
94.5
—
—
OpenECG-SimCLR arXiv’25
11M
46.9
91.5
73.1
92.4
52.3
95.1
OpenECG-BYOL arXiv’25
11M
47.7
91.1
72.8
92.6
51.5
94.8
OpenECG-MAE arXiv’25
11M
48.1
90.9
74.5
93.2
50.8
94.2
TABLE III: ECG classification: macro-F1 and macro-AUROC in %. Our results are means over three seeds; baselines are quoted from PhysioWave. Bold purple : highest reported value; underline : second highest.
EPN-612
GRABMyo
Method
Params
Acc.
F1
Acc.
F1
MOMENT ICML’24
385M
90.87
90.16
82.67
82.19
OTiS arXiv’24
45M
87.55
88.03
79.38
78.80
PhysioWave-S NeurIPS’25
5M
93.12
93.40
85.26
85.03
PhysioWave-B NeurIPS’25
15M
93.68
93.91
87.40
87.16
PhysioWave-L NeurIPS’25
37M
94.50
94.56
88.53
88.37
TABLE IV: sEMG gesture recognition: accuracy and macro-F1 in %. Our runs are means over three seeds; EPN-612 baselines retain their published values. Bold purple : highest reported value; underline : second highest.
Fig. 7: Seizure detection on SeizeIT2 (official split, 29 test patients, 2,912 h, 181 seizures). (a) Event-level sensitivity against false alarms per hour for the three fusion rules over the frozen PhysioWave-T encoders and for each EEG-only encoder at its better of frozen and fine-tuned; the dotted line is the 11 false alarms per hour of the dataset paper’s SVM. (b) Frozen and fine-tuned EEG encoders at ≤ 11 false alarms per hour, with encoder size. (c) RALF’s predicted reliability on clean inputs and with one modality corrupted at severity 0.7; the ringed point is the corrupted modality. (d) Window-level AUPRC of every modality subset. The RALF line is the original training configuration; the shaded band in (a) and (d) is the min–max over six RALF training variants, the original and five learning-rate and schedule settings.
P300
KaggleERN
Variant
BAC
AUROC
BAC
AUROC
Δ
PhysioWave-T (full)
67.1
73.7
61.7
66.3
—
Scale folding (vs. dynamic fold)
Scale expansion
66.8
73.4
61.4
66.0
−0.3
Static uniform fold ( α=u )
65.6
72.0
60.2
64.5
−1.6
w/o synthesis filters ( gs=δ )
66.4
73.0
61.0
65.6
−0.7
TABLE V: EEG ablations on PhysioNet-P300 and KaggleERN, averaged over three seeds. Metrics are percentages. Δ is the mean change across the four metrics relative to the full model; darker shading indicates a larger decrease.
Fig. 8: EEG encoder efficiency on one A100 in bf16, averaged over three seeds. (a) Latency per window. (b) Peak memory per batch. (c) Savings versus token count.
Fig. 9: Spatial structure in channel embeddings. (a) Embedding similarity versus geodesic scalp distance, with an untrained table for comparison. (b) Electrode-centered similarity maps; links mark the five nearest neighbors.
Fig. 10: Spectral adaptation of the wavelet front ends. (a) Level-one analysis responses before and after pre-training, with physiological bands and −3 dB cutoffs. (b) Selector weights at levels 1–3. (c) Low-pass cutoff changes.
Fig. 11: Scale allocation across sleep stages. (a) Stage-wise folding weights with 95 % subject-level confidence intervals. (b) Within-subject changes relative to wake. (c) Slowest-scale weight versus δ -band power share. Rows show Fpz-Cz and Pz-Oz.
Time-series foundation models are pretrained sequence models designed to transfer across forecasting, classification, anomaly detection, and other temporal tasks.